Low-light images have low brightness and contrast, which presents a huge obstacle to computer vision tasks. Low-light image enhancement is challenging because multiple factors (such as brightness, contrast, artifacts, and noise) must be considered simultaneously. In this study, we propose a neural network—a progressive-recursive image enhancement network (PRIEN)—to enhance low-light images. The main idea is to use a recursive unit, composed of a recursive layer and a residual block, to repeatedly unfold the input image for feature extraction. Unlike in previous methods, in the proposed study, we directly input low-light images into the dual attention model for global feature extraction. Next, we use a combination of recurrent layers and residual blocks for local feature extraction. Finally, we output the enhanced image. Furthermore, we input the global feature map of dual attention into each stage in a progressive way. In the local feature extraction module, a recurrent layer shares depth features across stages. In addition, we perform recursive operations on a single residual block, significantly reducing the number of parameters while ensuring good network performance. Although the network structure is simple, it can produce good results for a range of low-light conditions. We conducted experiments on widely adopted datasets. The results demonstrate the advantages of our method compared with other methods, from both qualitative and quantitative perspectives.

Lubrication plays a key role in successful manufacturing of pharmaceutical solid dosage forms; lubricants are essential ingredients in robust formulations to achieve this. Although many failures in pharmaceutical manufacturing operations are caused by issues related to lubrication, in general, lubricants do not gain adequate attention in the development of pharmaceutical formulations. In this paper, the fundamental background on lubrication is introduced, in which the relationships between lubrication and friction/adhesion forces are discussed. Then, the application of lubrication in the development of pharmaceutical products and manufacturing processes is discussed with an emphasis on magnesium stearate. In particular, the effect of its hydration state (anhydrate, monohydrate, dihydrate, and trihydrate) and its powder characteristics on lubrication efficiency, as well as product and process performance is summarized. In addition, the impact of lubrication on the dynamics of compaction/compression processes and on the mechanical properties of compacts/tablets is presented. Furthermore, the online monitoring of magnesium stearate in a blending process is briefly mentioned. Finally, the chemical compatibility of active pharmaceutical ingredient (API) with magnesium stearate and its reactive impurities is reviewed with examples from the literature illustrating the various reaction mechanisms involved.

To fully utilize spatial information for segmentation and address the challenge of handling areas with significant grayscale variations in remote sensing segmentation, we propose the spatial and frequency domain fusion network (SFFNet) framework. This framework employs a two-stage network design: the first stage extracts features using spatial methods to obtain features with sufficient spatial details and semantic information; the second stage maps these features in both spatial and frequency domains. In the frequency domain mapping, we introduce the wavelet transform feature decomposer (WTFD) structure, which decomposes features into low-frequency and high-frequency components using the Haar wavelet transform and integrates them with spatial features. To bridge the semantic gap between frequency and spatial features, facilitating significant feature selection to promote the combination of features from different representation domains, we design the multiscale dual-representation alignment filter (MDAF). This structure utilizes multiscale convolutions and dual-cross attentions. Comprehensive experimental results demonstrate that, compared to existing methods, SFFNet achieves superior performance in terms of mean intersection over union (mIoU), reaching 84.80% and 87.73%, respectively. The code is located at https://github.com/yysdck/SFFNet .

There is a series of image degradation in the image acquired in haze and other weather. The single image dehazing is a challenging and ill-posed problem. Using deep neural networkd methods, it solve the drawbacks of manually designing haze-related features. The paper proposes a dehazing algorithm using residual-based deep CNN. The network model is divided into two phases: in the first stage, a haze image is input and the transmission map is estimated by network; in the second stage, the ratio of foggy image and transmission map is used as input, and the residual network is used to remove haze. It avoids the estimation of atmospheric light and improves the efficiency of dehazing. To train the proposed network, we use the NYU2 depth dataset as the training set. In the full-reference metric PSNR, SSIM, FSIM and no-reference metric SSEQ, BRISQUE, NIQE aspect, the experimental results confirm the efficiency and robustness of the proposed method.

The absorption and scattering caused by the underwater medium degrade the quality of underwater optical imaging, which limits the further development of underwater tasks. Recently, transformer-based methods have shown the same excellent performance as convolutional neural networks (CNNs) in various vision tasks, but the huge parameters of such networks hinder their application deployment. In this article, we propose novel adaptive group attention (AGA), which can dynamically select visually complementary channels based on the dependencies, reducing the number of further attention parameters. The AGA is applied in the Swin Transformer module and used to design an end-to-end underwater image enhancement network. The network also introduces the multiscale cascade module and the channel attention mechanism. This article conducted ablation study and qualitative and quantitative comparisons on public datasets, and the results show that the application of AGA significantly compresses the model size while ensuring performance, and other application components have the significant gain on the network. Compared with other advanced methods, the network in this article has outstanding performance.

Video super-resolution techniques aim to obtain high-resolution equivalents of existing low-resolution videos through a series of operations. In recent research, transformers have been increasingly popular because of their remarkable abilities in parallel computing and efficient extraction of space-time sequence features from videos. Moreover, combining self-attention and multi-scale methods has yielded excellent results. However, the combination of the two methods has limitations, current up-sampling methods struggle to match the global modeling capacity of self-attention mechanisms. Therefore, this paper proposes three strategies to combine the two methods. Based on the approximation strategy, we first construct a new bilinear up-sampling method for multi-scale acquisition. Convolution and cross-attention techniques are then used to correct and align features at different scales to prevent large deviations in feature extraction at a specific scale, which can affect subsequent feature extraction. Finally, to effectively solve the common computational complexity, C ⁰ continuity, and neuron death problems of existing activation functions, a new method to construct the activation function is proposed. The cubic spline function is used to construct a new activation function approximating tanh. The new activation function is C ² continuous, which is piecewise defined by cubic polynomial curves. In this study, better results were achieved on three public video super-resolution test sets: REDS4, Vid4, and Vimeo-90K-T. Experiments demonstrated that the proposed method could provide a new solution for video super-resolution tasks.